Research on Extracting Keywords from Agglutinative Languages Based on Stem Units

Uyghur and Kazakh are typical agglutinative languages. Semantic and syntactic lexicons are derived from stems or roots by adding affixes. A keyword in a sentence can be the notional particles which are the semantic stems. The stems in derivative lexicons are deformed or harmonized with annexed affixes, so a special stem extraction process is necessary. This paper proposes a keyword extraction method based on a neural network stemming model. In order to verify the effectiveness of stem unit, keyword extraction is carried out on both word and stem units respectively. The experimental results show that the effects of keywords extraction through the above two particles are in obvious contrast. The keyword extracted by stemming has the best results, and the quality and efficiency of the extracted keywords are greatly improved.